Final_Assignment_Template

Sleeping

App Files Files Community

Final_Assignment_Template / app.py

atulsachan

Claude Opus 4.8 (1M context)

Implement GAIA agent with smolagents + Claude

0c10a0b 4 months ago

Raw History Blame Contribute Delete

13.2 kB

import os
import sys

# --- Make stdout/stderr UTF-8 so emoji prints don't crash on Windows consoles ---
try:
    sys.stdout.reconfigure(encoding="utf-8")
    sys.stderr.reconfigure(encoding="utf-8")
except Exception:
    pass

# --- Trust the OS certificate store (needed behind corporate TLS-inspection proxies) ---
try:
    import truststore
    truststore.inject_into_ssl()
except Exception as _e:
    print(f"truststore not active ({_e}); TLS verification uses certifi defaults.")

# --- Load secrets from .env (ANTHROPIC_API_KEY, HF_TOKEN, MODEL_ID) ---
try:
    from dotenv import load_dotenv
    load_dotenv()
except Exception:
    pass

import gradio as gr
import requests
import inspect
import pandas as pd

from smolagents import (
    CodeAgent,
    LiteLLMModel,
    DuckDuckGoSearchTool,
    VisitWebpageTool,
    tool,
)

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# GAIA requires an EXACT-match final answer. This template steers Claude to emit
# only the answer, formatted per the official GAIA rules.
GAIA_PROMPT_TEMPLATE = """You are a general AI assistant solving a question from the GAIA benchmark.
The task_id for this question is: {task_id}
If the question refers to an attached file (spreadsheet, code, audio, etc.), call
`download_task_file("{task_id}")` to fetch it to local disk, then inspect it with Python.
Work step by step using your tools (web search, visiting web pages, running Python,
downloading the task file, transcribing audio). Then give your final answer.
YOUR FINAL ANSWER must be the answer ONLY — a number, OR as few words as possible,
OR a comma-separated list of numbers and/or strings.
- If asked for a number: use digits only, no thousands separators, no units
  (no $, %, etc.) unless the question explicitly asks for them.
- If asked for a string: no articles, no abbreviations (write city names in full),
  and write digits in plain text unless told otherwise.
- If asked for a comma-separated list: apply the rules above to each element.
Question:
{question}
"""


# --- Agent tools ---------------------------------------------------------------
@tool
def download_task_file(task_id: str) -> str:
    """Download the file attached to a GAIA task and return the local file path.
    Args:
        task_id: The task_id of the question whose attached file should be downloaded.
    """
    os.makedirs(".agent_files", exist_ok=True)
    url = f"{DEFAULT_API_URL}/files/{task_id}"
    resp = requests.get(url, timeout=60)
    resp.raise_for_status()

    # Prefer the server-provided filename, fall back to the task_id.
    filename = task_id
    disposition = resp.headers.get("content-disposition", "")
    if "filename=" in disposition:
        filename = disposition.split("filename=")[-1].strip().strip('"')

    path = os.path.join(".agent_files", filename)
    with open(path, "wb") as fh:
        fh.write(resp.content)
    return path


@tool
def transcribe_audio(file_path: str) -> str:
    """Transcribe a local audio file (e.g. .mp3) to text using a speech-to-text model.
    Args:
        file_path: Local path to the audio file to transcribe.
    """
    from huggingface_hub import InferenceClient

    client = InferenceClient(token=os.getenv("HF_TOKEN"))
    result = client.automatic_speech_recognition(file_path)
    return getattr(result, "text", str(result))


# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        if not os.getenv("ANTHROPIC_API_KEY"):
            raise RuntimeError(
                "ANTHROPIC_API_KEY is not set. Add it to the .env file in this folder."
            )
        model_id = os.getenv("MODEL_ID", "anthropic/claude-sonnet-4-6")
        self.model = LiteLLMModel(model_id=model_id)

        tools = [
            DuckDuckGoSearchTool(),
            VisitWebpageTool(),
            download_task_file,
            transcribe_audio,
        ]
        # Wikipedia search is nice-to-have; skip gracefully if its dependency is missing.
        try:
            from smolagents import WikipediaSearchTool
            tools.append(WikipediaSearchTool())
        except Exception as e:
            print(f"Wikipedia tool unavailable, continuing without it: {e}")

        self.agent = CodeAgent(
            tools=tools,
            model=self.model,
            additional_authorized_imports=[
                "pandas", "openpyxl", "numpy", "math", "statistics",
                "datetime", "json", "re", "itertools", "collections", "csv",
            ],
            max_steps=20,
        )
        print(f"BasicAgent initialized with model '{model_id}'.")

    def __call__(self, question: str, task_id: str | None = None) -> str:
        print(f"Agent received question (first 80 chars): {question[:80]}...")
        prompt = GAIA_PROMPT_TEMPLATE.format(task_id=task_id or "(none)", question=question)
        answer = str(self.agent.run(prompt)).strip()
        print(f"Agent returning answer: {answer[:200]}")
        return answer

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code

    if profile:
        username= f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent()
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
        if not questions_data:
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response from questions endpoint: {e}")
         print(f"Response text: {response.text[:500]}")
         return f"Error decoding server response for questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            submitted_answer = agent(question_text, task_id)
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
        except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
        ---
        **Disclaimers:**
        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    # Removed max_rows=10 from DataFrame constructor
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup: # Print repo URLs if SPACE_ID is found
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)

	import os
	import sys

	# --- Make stdout/stderr UTF-8 so emoji prints don't crash on Windows consoles ---
	try:
	sys.stdout.reconfigure(encoding="utf-8")
	sys.stderr.reconfigure(encoding="utf-8")
	except Exception:
	pass

	# --- Trust the OS certificate store (needed behind corporate TLS-inspection proxies) ---
	try:
	import truststore
	truststore.inject_into_ssl()
	except Exception as _e:
	print(f"truststore not active ({_e}); TLS verification uses certifi defaults.")

	# --- Load secrets from .env (ANTHROPIC_API_KEY, HF_TOKEN, MODEL_ID) ---
	try:
	from dotenv import load_dotenv
	load_dotenv()
	except Exception:
	pass

	import gradio as gr
	import requests
	import inspect
	import pandas as pd

	from smolagents import (
	CodeAgent,
	LiteLLMModel,
	DuckDuckGoSearchTool,
	VisitWebpageTool,
	tool,
	)

	# (Keep Constants as is)
	# --- Constants ---
	DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

	# GAIA requires an EXACT-match final answer. This template steers Claude to emit
	# only the answer, formatted per the official GAIA rules.
	GAIA_PROMPT_TEMPLATE = """You are a general AI assistant solving a question from the GAIA benchmark.

	The task_id for this question is: {task_id}
	If the question refers to an attached file (spreadsheet, code, audio, etc.), call
	`download_task_file("{task_id}")` to fetch it to local disk, then inspect it with Python.

	Work step by step using your tools (web search, visiting web pages, running Python,
	downloading the task file, transcribing audio). Then give your final answer.

	YOUR FINAL ANSWER must be the answer ONLY — a number, OR as few words as possible,
	OR a comma-separated list of numbers and/or strings.
	- If asked for a number: use digits only, no thousands separators, no units
	(no $, %, etc.) unless the question explicitly asks for them.
	- If asked for a string: no articles, no abbreviations (write city names in full),
	and write digits in plain text unless told otherwise.
	- If asked for a comma-separated list: apply the rules above to each element.

	Question:
	{question}
	"""


	# --- Agent tools ---------------------------------------------------------------
	@tool
	def download_task_file(task_id: str) -> str:
	"""Download the file attached to a GAIA task and return the local file path.

	Args:
	task_id: The task_id of the question whose attached file should be downloaded.
	"""
	os.makedirs(".agent_files", exist_ok=True)
	url = f"{DEFAULT_API_URL}/files/{task_id}"
	resp = requests.get(url, timeout=60)
	resp.raise_for_status()

	# Prefer the server-provided filename, fall back to the task_id.
	filename = task_id
	disposition = resp.headers.get("content-disposition", "")
	if "filename=" in disposition:
	filename = disposition.split("filename=")[-1].strip().strip('"')

	path = os.path.join(".agent_files", filename)
	with open(path, "wb") as fh:
	fh.write(resp.content)
	return path


	@tool
	def transcribe_audio(file_path: str) -> str:
	"""Transcribe a local audio file (e.g. .mp3) to text using a speech-to-text model.

	Args:
	file_path: Local path to the audio file to transcribe.
	"""
	from huggingface_hub import InferenceClient

	client = InferenceClient(token=os.getenv("HF_TOKEN"))
	result = client.automatic_speech_recognition(file_path)
	return getattr(result, "text", str(result))


	# --- Basic Agent Definition ---
	# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
	class BasicAgent:
	def __init__(self):
	if not os.getenv("ANTHROPIC_API_KEY"):
	raise RuntimeError(
	"ANTHROPIC_API_KEY is not set. Add it to the .env file in this folder."
	)
	model_id = os.getenv("MODEL_ID", "anthropic/claude-sonnet-4-6")
	self.model = LiteLLMModel(model_id=model_id)

	tools = [
	DuckDuckGoSearchTool(),
	VisitWebpageTool(),
	download_task_file,
	transcribe_audio,
	]
	# Wikipedia search is nice-to-have; skip gracefully if its dependency is missing.
	try:
	from smolagents import WikipediaSearchTool
	tools.append(WikipediaSearchTool())
	except Exception as e:
	print(f"Wikipedia tool unavailable, continuing without it: {e}")

	self.agent = CodeAgent(
	tools=tools,
	model=self.model,
	additional_authorized_imports=[
	"pandas", "openpyxl", "numpy", "math", "statistics",
	"datetime", "json", "re", "itertools", "collections", "csv",
	],
	max_steps=20,
	)
	print(f"BasicAgent initialized with model '{model_id}'.")

	def __call__(self, question: str, task_id: str \| None = None) -> str:
	print(f"Agent received question (first 80 chars): {question[:80]}...")
	prompt = GAIA_PROMPT_TEMPLATE.format(task_id=task_id or "(none)", question=question)
	answer = str(self.agent.run(prompt)).strip()
	print(f"Agent returning answer: {answer[:200]}")
	return answer

	def run_and_submit_all( profile: gr.OAuthProfile \| None):
	"""
	Fetches all questions, runs the BasicAgent on them, submits all answers,
	and displays the results.
	"""
	# --- Determine HF Space Runtime URL and Repo URL ---
	space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code

	if profile:
	username= f"{profile.username}"
	print(f"User logged in: {username}")
	else:
	print("User not logged in.")
	return "Please Login to Hugging Face with the button.", None

	api_url = DEFAULT_API_URL
	questions_url = f"{api_url}/questions"
	submit_url = f"{api_url}/submit"

	# 1. Instantiate Agent ( modify this part to create your agent)
	try:
	agent = BasicAgent()
	except Exception as e:
	print(f"Error instantiating agent: {e}")
	return f"Error initializing agent: {e}", None
	# In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
	agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
	print(agent_code)

	# 2. Fetch Questions
	print(f"Fetching questions from: {questions_url}")
	try:
	response = requests.get(questions_url, timeout=15)
	response.raise_for_status()
	questions_data = response.json()
	if not questions_data:
	print("Fetched questions list is empty.")
	return "Fetched questions list is empty or invalid format.", None
	print(f"Fetched {len(questions_data)} questions.")
	except requests.exceptions.RequestException as e:
	print(f"Error fetching questions: {e}")
	return f"Error fetching questions: {e}", None
	except requests.exceptions.JSONDecodeError as e:
	print(f"Error decoding JSON response from questions endpoint: {e}")
	print(f"Response text: {response.text[:500]}")
	return f"Error decoding server response for questions: {e}", None
	except Exception as e:
	print(f"An unexpected error occurred fetching questions: {e}")
	return f"An unexpected error occurred fetching questions: {e}", None

	# 3. Run your Agent
	results_log = []
	answers_payload = []
	print(f"Running agent on {len(questions_data)} questions...")
	for item in questions_data:
	task_id = item.get("task_id")
	question_text = item.get("question")
	if not task_id or question_text is None:
	print(f"Skipping item with missing task_id or question: {item}")
	continue
	try:
	submitted_answer = agent(question_text, task_id)
	answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
	results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
	except Exception as e:
	print(f"Error running agent on task {task_id}: {e}")
	results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})

	if not answers_payload:
	print("Agent did not produce any answers to submit.")
	return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

	# 4. Prepare Submission
	submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
	status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
	print(status_update)

	# 5. Submit
	print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
	try:
	response = requests.post(submit_url, json=submission_data, timeout=60)
	response.raise_for_status()
	result_data = response.json()
	final_status = (
	f"Submission Successful!\n"
	f"User: {result_data.get('username')}\n"
	f"Overall Score: {result_data.get('score', 'N/A')}% "
	f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
	f"Message: {result_data.get('message', 'No message received.')}"
	)
	print("Submission successful.")
	results_df = pd.DataFrame(results_log)
	return final_status, results_df
	except requests.exceptions.HTTPError as e:
	error_detail = f"Server responded with status {e.response.status_code}."
	try:
	error_json = e.response.json()
	error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
	except requests.exceptions.JSONDecodeError:
	error_detail += f" Response: {e.response.text[:500]}"
	status_message = f"Submission Failed: {error_detail}"
	print(status_message)
	results_df = pd.DataFrame(results_log)
	return status_message, results_df
	except requests.exceptions.Timeout:
	status_message = "Submission Failed: The request timed out."
	print(status_message)
	results_df = pd.DataFrame(results_log)
	return status_message, results_df
	except requests.exceptions.RequestException as e:
	status_message = f"Submission Failed: Network error - {e}"
	print(status_message)
	results_df = pd.DataFrame(results_log)
	return status_message, results_df
	except Exception as e:
	status_message = f"An unexpected error occurred during submission: {e}"
	print(status_message)
	results_df = pd.DataFrame(results_log)
	return status_message, results_df


	# --- Build Gradio Interface using Blocks ---
	with gr.Blocks() as demo:
	gr.Markdown("# Basic Agent Evaluation Runner")
	gr.Markdown(
	"""
	Instructions:

	1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
	2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
	3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

	---
	Disclaimers:
	Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
	This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
	"""
	)

	gr.LoginButton()

	run_button = gr.Button("Run Evaluation & Submit All Answers")

	status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
	# Removed max_rows=10 from DataFrame constructor
	results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

	run_button.click(
	fn=run_and_submit_all,
	outputs=[status_output, results_table]
	)

	if __name__ == "__main__":
	print("\n" + "-"30 + " App Starting " + "-"30)
	# Check for SPACE_HOST and SPACE_ID at startup for information
	space_host_startup = os.getenv("SPACE_HOST")
	space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

	if space_host_startup:
	print(f"✅ SPACE_HOST found: {space_host_startup}")
	print(f" Runtime URL should be: https://{space_host_startup}.hf.space")
	else:
	print("ℹ️ SPACE_HOST environment variable not found (running locally?).")

	if space_id_startup: # Print repo URLs if SPACE_ID is found
	print(f"✅ SPACE_ID found: {space_id_startup}")
	print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}")
	print(f" Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
	else:
	print("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

	print("-"*(60 + len(" App Starting ")) + "\n")

	print("Launching Gradio Interface for Basic Agent Evaluation...")
	demo.launch(debug=True, share=False)